Efficient method identifies multiple power grid outages in real-time.
problem Identifying simultaneous line outages in large power networks is computationally challenging.
method Developed a 'Learning-to-Infer' method to efficiently infer every line status.
result The method achieves excellent performance in identifying multi-line outages in real-time with minimal labeled data.
Amortized Causal Discovery learns to infer causal graphs from time-series data, improving performance.
problem Inference of causal graphs from time-series data is inefficient due to fitting new models for each sample.
method Proposes Amortized Causal Discovery, a variational model that leverages shared dynamics across samples with different causal graphs.
result Significant improvements in causal discovery performance demonstrated experimentally.
Automates UI implementation from designer images.
problem Automating UI implementation from designer images.
method Generative model training and imitation learning.
result 92.5% accuracy on Android Button attribute inference.
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…
Proposes a constant memory iterative inverse model using invertible networks.
problem Memory limitations in iterative learning approaches for inverse problems.
method Invertible networks to avoid storing intermediate activations, constant memory model.
result Trains 400-layer models on 3D MRI volumes, achieving state-of-the-art image reconstruction.
Bayesian meta-learning method learns uncertainty from few data.
problem Learning uncertainty from limited data in meta-learning.
method Combines gradient-based meta-learning with nonparametric variational inference.
result Robust meta-update mechanism prevents overfitting.
This work characterizes reward function partial identifiability and its impact on policy optimization.
problem Reward function partial identifiability in complex tasks.
method Formal characterisation of partial identifiability using various reward learning data sources.
result Unified framework for comparing data sources and downstream tasks by their invariances.
NRI model learns interactions from data without labels.
problem Learning interactions in systems from unlabeled data.
method Variational auto-encoder with graph neural networks.
result NRI model accurately recovers interactions and predicts dynamics.
ARTree uses deep learning to infer tree topologies efficiently.
problem Efficient phylogenetic inference from tree topologies.
method Deep autoregressive model based on graph neural networks (GNNs).
result ARTree provides a flexible family of distributions over tree topologies.
New approach allows deep learning to adapt to new tasks without explicit training.
problem How to reuse deep learning knowledge for new tasks without explicit training.
method Homoiconic Meta-Mapping (HoMM) that transforms task representations.
result Zero-shot remapping of behavior to adapt to new tasks.
LCIT tests conditional independence using latent representations.
problem Detecting conditional independencies in statistical and machine learning tasks.
method Generative framework for learning latent representations of target variables X and Y, then testing for remaining dependencies.
result LCIT outperforms state-of-the-art baselines consistently under different metrics and settings.
Paper proposes Meta Label Learning to infer global labels for robust few-shot models.
problem Few-shot learning with limited training data.
method Meta Label Learning (MeLa) framework that infers global labels.
result MeLa framework is competitive with existing methods and robust for few-shot learning.
Crowdlab uses classifiers to estimate consensus labels and annotator quality.
problem Leveraging multiple annotators for data classification.
method Weighted ensemble approach using any trained classifier.
result Superior estimates for consensus labels and annotator quality.
A new approach to learning in brain-like networks using adversarial algorithms.
problem Complex inter-dependencies in brain-like networks not compatible with conditional independence assumptions.
method Adversarial algorithm for learning models of perceptual processing.
result The approach can mimic known neural phenomena and yields testable hypotheses.
Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.
problem Efficiently adapt and explore in-context without gradient-based updates.
method Uses a transformer to learn inference from training tasks, considering hypothesis space of partial models.
result Adaptation speed and exploration-exploitation balance approach those of an exact posterior sampling oracle.
Classi-Fly uses machine learning to infer aircraft categories from open data.
problem Lack of metadata for aircraft in open data sources.
method Machine learning approach based on aircraft movement patterns.
result Correct aircraft category inference with over 88% accuracy.
A neural network learns to control a two-link arm with non-linear dynamics.
problem Training spiking neural networks to control complex, non-linear systems.
method Feedback-based Online Local Learning Of Weights (FOLLOW) to train a network of spiking neurons with hidden layers.
result The network learns an inverse model of the arm's dynamics and uses it to generate a motor command for control.
The paper proposes a model to learn motion perception in V1 using vector and matrix representations.
problem Motion perception in primary visual cortex (V1).
method Coupling vector representations of local contents and matrix representations of local pixel displacements.
result The model can learn Gabor-like filter pairs and infer local motions.
CSML learns causal structures for few-shot learning.
problem Spurious correlations limit deep learning generalization.
method CSML combines perception, causal induction, and reasoning modules.
result CSML achieves superior few-shot learning across tasks.
Hybrid model combines graphical and learned inference for better data estimation.
problem Suboptimal estimation due to poor graphical model approximation of complex data generating process.
method Combines graphical inference with a learned inverse model structured as a graph neural network and formulated as a recurrent neural network.
result Hybrid model estimates chaotic trajectory more accurately than graphical or learned inference alone.
Model infers temporal connections in dynamic graphs from node interactions.
problem Challenges in reasoning about evolving graphs, especially with human-specified edges.
method Temporal point processes and variational autoencoders with bilinear interactions.
result Model outperforms baselines and infers semantically interpretable connections.
Meta-agent learns effective exploration from offline data.
problem Design a meta-agent to quickly maximize reward in unseen tasks.
method Bayesian RL approach with adaptive neural belief estimate.
result Meta-agent learns effective exploration behavior from diverse tasks.
TossingBot learns to throw objects accurately with residual physics.
problem Learning to throw arbitrary objects accurately and quickly.
method End-to-end formulation that learns control parameters from visual observations.
result TossingBot achieves 600+ grasps per hour with 85% throwing accuracy.
Single model learns physics from diverse data.
problem Lack of universal physics models for diverse applications.
method General Physics Transformer (GPhyT) trained on diverse physics data.
result Single model achieves superior performance across multiple physics domains.
Genetic algorithms optimize neural networks for cosmological data analysis.
problem Inaccurate results from neural networks due to poor hyperparameter selection.
method Used genetic algorithms to optimize hyperparameters of neural networks.
result Genetic algorithms improve neural network performance in cosmological data analysis.
Crowdsourcing estimates labels from group intuitions.
problem Difficulty in traditional labeling for complex data.
method Ballpark Learning for group-based inference.
result Crowd estimates rival supervised models.
Generative grading improves automated feedback for structured problems.
problem Difficulty in providing high-quality feedback on structured assignments.
method Generative descriptions of student cognition, probabilistic programs, and learning to infer feedback.
result Achieved near-human accuracy in grading and feedback across diverse domains.
Deep Learning predicts e-commerce activity from Italian enterprise websites.
problem Predicting e-commerce activity from Italian enterprise websites.
method Developed a sophisticated processing pipeline using Convolutional Neural Networks and Word Embeddings.
result Deep Learning outperforms traditional Machine Learning methods for text classification.
HFM uses deep learning to infer fluid dynamics from visual data.
problem Data assimilation of fluid dynamics from flow visualizations.
method Physics-informed deep learning framework based on Navier-Stokes equations.
result Accurate predictions of velocity and pressure fields in complex flows.
Combines ML and DA to infer unresolved scale parametrisation from noisy data.
problem Training ML-based parametrisations from realistic, noisy and sparse observations.
method Two-step process: DA for state estimation, ML for model error prediction.
result Hybrid model produces better forecasts and attractor representation.
ProbE model improves relational implication detection to 0.8143.
problem Improving inference of relational data to extract more useful information.
method Formal probabilistic model of relational implication using estimators based on empirical distribution.
result ProbE model outperforms existing approaches, achieving 0.8143 AUC on evaluation dataset.
This work improves the accuracy of OEF and DBV maps from qBOLD MRI data.
problem Noisy and inaccurate inference of OEF and DBV from qBOLD MRI data.
method Flexible amortized variational inference using a scaled multivariate logit-Normal distribution.
result Smooth and physiologically plausible OEF and DBV maps inferred with fewer training data.
A deep model learns to infer fluorescence labels from unlabeled microscopy images.
problem Challenges in obtaining high quality images of cellular structures due to complex environments and label staining limitations.
method Developed a novel deep model using global pixel transformer layers and dense blocks, incorporating multi-scale input strategy.
result Significantly outperforms state-of-the-art methods in fluorescence image prediction tasks.
This study uses deep learning to infer stellar parameters from short TESS and K2 observations.
problem Inferring precise stellar parameters from short-duration TESS and K2 observations.
method Developed a machine learning algorithm to infer asteroseismic parameters from one-month-long TESS observations of red giants.
result The algorithm can accurately infer Δν and νmax for approximately 50% of TESS samples and ΔΠ1 for about 200 young red-giants from K2. Estimates users' preference for a site over others using engagement data.
problem Lack of data on users' interactions with other sites makes it hard to estimate preferences for a focal site.
method Uses Hierarchical Bayes Method with two estimation techniques: Markov Chain Monte Carlo and Stochastic Gradient with Langevin Dynamics.
result Good support found for the approach to computing personalized share of engagement.
New method uses manifold learning to infer latent positions of 1D submanifolds in random dot product graphs.
problem Inference on latent positions of unknown 1D submanifolds in RDPGs.
method Apply Isomap for manifold learning to estimate arc lengths on the unknown submanifold.
result Test statistics based on Isomap converge to known submanifold power as auxiliary vertices increase.